29 citations · 48 across the 24 of their papers we have counts for
26 papers
Predictive Semantic Safety: From Visual Physical Reasoning to Safety-Critical Control
Taekyung Kim, Salem Fradi, Yanning Dai +2
Physical interactions can create future hazards that are not apparent from the robot's current geometric surroundings. We present a framework termed Predictive Semantic Safety (PSS…
Hybrid Advantage Estimation with Unified Critic for VLM Agentic Reinforcement Learning
Wenxuan Zhang, Yuhui Wang, Donggang Jia +5
Large Vision-Language Models (VLMs) now act as agents in interactive environments, where success requires coherent reasoning and decision-making across turns. Although end-to-end t…
CORAL: Learning Amyloid Fibril Ligand Docking with Cooperative Binding Rewards
Yasheng Sun, Bohan Li, Youqi Tao +1
A hallmark of neurodegenerative diseases such as Alzheimer's and Parkinson's is the aberrant aggregation of proteins into amyloid fibrils, and small molecules that selectively bind…
Learning to Forget: Continual Learning with Adaptive Weight Decay
Aditya A. Ramesh, Alex Lewandowski, Jürgen Schmidhuber
Continual learning agents with finite capacity must balance acquiring new knowledge with retaining the old. This requires controlled forgetting of knowledge that is no longer neede…
Neural Computers
Mingchen Zhuge, Changsheng Zhao, Haozhe Liu +16
We propose a new frontier: Neural Computers (NCs) that unify computation, memory, and I/O of traditional computers in a learned runtime state. Our long-term goal is the Completely…
Curious Causality-Seeking Agents Learn Meta Causal World
Zhiyu Zhao, Haoxuan Li, Haifeng Zhang +4
When building a world model, a common assumption is that the environment has a single, unchanging underlying causal rule, like applying Newton's laws to every situation. In reality…
On the Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision Transformers
Miroslav Štrupl, Oleg Szehr, Francesco Faccio +3
This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Tran…
Upside Down Reinforcement Learning with Policy Generators
Jacopo Di Ventura, Dylan R. Ashley, Vincent Herrmann +2
Upside Down Reinforcement Learning (UDRL) is a promising framework for solving reinforcement learning problems which focuses on learning command-conditioned policies. In this work,…
Goldfish: Vision-Language Understanding of Arbitrarily Long Videos
Kirolos Ataallah, Xiaoqian Shen, Eslam Abdelrahman +6
Most current LLM-based models for video understanding can process videos within minutes. However, they struggle with lengthy videos due to challenges such as "noise and redundancy"…
Highway Value Iteration Networks
Yuhui Wang, Weida Li, Francesco Faccio +2
Value iteration networks (VINs) enable end-to-end learning for planning tasks by employing a differentiable "planning module" that approximates the value iteration algorithm. Howev…
Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning
Aditya A. Ramesh, Kenny Young, Louis Kirsch +1
Temporal credit assignment in reinforcement learning is challenging due to delayed and stochastic outcomes. Monte Carlo targets can bridge long delays between action and consequenc…
Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning
Yuhui Wang, Qingyuan Wu, Dylan R. Ashley +4
The Value Iteration Network (VIN) is an end-to-end differentiable neural network architecture for planning. It exhibits strong generalization to unseen domains by incorporating a d…
Highway Reinforcement Learning
Yuhui Wang, Miroslav Strupl, Francesco Faccio +5
Learning from multi-step off-policy data collected by a set of policies is a core problem of reinforcement learning (RL). Approaches based on importance sampling (IS) often suffer…
Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable
Haozhe Liu, Wentian Zhang, Bing Li +2
Foundational generative models should be traceable to protect their owners and facilitate safety regulation. To achieve this, traditional approaches embed identifiers based on supe…
Towards a Robust Soft Baby Robot With Rich Interaction Ability for Advanced Machine Learning Algorithms
Mohannad Alhakami, Dylan R. Ashley, Joel Dunham +4
Advanced machine learning algorithms require platforms that are extremely robust and equipped with rich sensory feedback to handle extensive trial-and-error learning without relyin…
Faster Diffusion via Temporal Attention Decomposition
Haozhe Liu, Wentian Zhang, Jinheng Xie +6
We explore the role of attention mechanism during inference in text-conditional diffusion models. Empirical observations suggest that cross-attention outputs converge to a fixed po…
Learning Useful Representations of Recurrent Neural Network Weight Matrices
Vincent Herrmann, Francesco Faccio, Jürgen Schmidhuber
Recurrent Neural Networks (RNNs) are general-purpose parallel-sequential computers. The program of an RNN is its weight matrix. How to learn useful representations of RNN weights t…
Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays
Qingyuan Wu, Simon Sinong Zhan, Yixuan Wang +6
Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. State-of-the-art (SOTA) state augmentation techniques either s…
Efficient Rotation Invariance in Deep Neural Networks through Artificial Mental Rotation
Lukas Tuggener, Thilo Stadelmann, Jürgen Schmidhuber
Humans and animals recognize objects irrespective of the beholder's point of view, which may drastically change their appearances. Artificial pattern recognizers also strive to ach…
Guiding Online Reinforcement Learning with Action-Free Offline Pretraining
Deyao Zhu, Yuhui Wang, Jürgen Schmidhuber +1
Offline RL methods have been shown to reduce the need for environment interaction by training agents using offline collected episodes. However, these methods typically require acti…
Eliminating Meta Optimization Through Self-Referential Meta Learning
Louis Kirsch, Jürgen Schmidhuber
Meta Learning automates the search for learning algorithms. At the same time, it creates a dependency on human engineering on the meta-level, where meta learning algorithms need to…
Goal-Conditioned Generators of Deep Policies
Francesco Faccio, Vincent Herrmann, Aditya Ramesh +2
Goal-conditioned Reinforcement Learning (RL) aims at learning optimal policies, given goals encoded in special command inputs. Here we study goal-conditioned neural nets (NNs) that…
General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States
Francesco Faccio, Aditya Ramesh, Vincent Herrmann +2
Learning to evaluate and improve policies is a core problem of Reinforcement Learning (RL). Traditional RL algorithms learn a value function defined for a single policy. A recently…
Learning Relative Return Policies With Upside-Down Reinforcement Learning
Dylan R. Ashley, Kai Arulkumaran, Jürgen Schmidhuber +1
Lately, there has been a resurgence of interest in using supervised learning to solve reinforcement learning problems. Recent work in this area has largely focused on learning comm…